Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1857 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0621. Min Range: -6.0621
Max Act: 6.0621. Min Act: -0.1700
Data Index: 2270801 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.8746. Min Act: -0.1700
Data Index: 5549422 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.8433. Min Act: -0.1700
Data Index: 2773141 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5750602 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.7183. Min Act: -0.1700
Data Index: 7176492 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6871. Min Act: -0.1700
Data Index: 1050907 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6871. Min Act: -0.1700
Data Index: 4696256 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6871. Min Act: -0.1700
Data Index: 7958628 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6558. Min Act: -0.1700
Data Index: 6277653 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6246. Min Act: -0.1700
Data Index: 3776052 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6246. Min Act: -0.1700
Data Index: 7725322 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6558. Min Act: -0.1700
Data Index: 1196242 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6246. Min Act: -0.1700
Data Index: 7080927 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6558. Min Act: -0.1700
Data Index: 8546859 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5933. Min Act: -0.1700
Data Index: 4294965 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5933. Min Act: -0.1700
Data Index: 750529 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5621. Min Act: -0.1700
Data Index: 8326140 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5621. Min Act: -0.1700
Data Index: 1484892 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5308. Min Act: -0.1700
Data Index: 770817 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5621. Min Act: -0.1700
Data Index: 7326267 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19